python爬虫—爬取百度百科数据

爬虫框架：开发平台 centos6.7 根据慕课网爬虫教程编写代码片区百度百科url，标题，内容

分为4个模块:html_downloader.py 下载器

html_outputer.py 爬取数据生成html模块

html_parser 获取有用数据

url_manager url管理器

spider_main 爬虫启动代码

spider_main.py

 1 #!/usr/bin/python
 2 #-*- coding: utf8 -*-
 3 
 4 import html_downloader
 5 import html_outputer
 6 import html_parser
 7 import url_manager
 8 
 9 class SpiderMain(object):
10     def __init__(self):
11         #初始化url管理器
12         self.urls = url_manager.UrlManager()
13         #初始化url下载器
14         self.downloader = html_downloader.HtmlDownloader()
15         #初始化url解析器
16         self.parser = html_parser.HtmlParser()
17         #初始化url输出
18         self.outputer = html_outputer.HtmlOutputer()
19 
20     def craw(self, root_url):
21         count = 1
22         #url管理器中添加一个new url
23         self.urls.add_new_url(root_url)
24         #判断是否有新的URL 开始爬取
25         while self.urls.has_new_url():
26             try:
27                 #得到新的url
28                 new_url = self.urls.get_new_url()
29                 print 'craw %d : %s' % (count, new_url)
30                 #下载新的url的数据
31                 html_cont = self.downloader.download(new_url)
32                 #解析出来url的内容和地址
33                 new_urls, new_data = self.parser.parse(new_url, html_cont)
34                 #新的url补充进url管理器
35                 self.urls.add_new_urls(new_urls)
36                 #输出数据
37                 self.outputer.collect_data(new_data)
38 
39                 if count == 1001:
40                     break
41                 count = count + 1
42                 print count
43             except:

html_parser.py

 1 #!/bin/usr/python 
 2 #-*- coding:utf8 -*-
 3 
 4 from bs4 import BeautifulSoup
 5 import re
 6 import urlparse
 7 
 8 class HtmlParser(object):
 9     '''
10     解析器
11     '''
12     
13     def _get_new_urls(self, page_url, soup):
14         new_urls = set()
15         links = soup.find_all('a', href=re.compile(r"/view/d+.htm"))
16         for link in links:
17             new_url = link['href']
18             new_full_url = urlparse.urljoin(page_url, new_url)
19             new_urls.add(new_full_url)
20         
21 
22         return new_urls
23     
24     def _get_new_data(self, page_url, soup):
25         res_data = {}
26 
27         res_data['url'] = page_url
28 
29         title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find('h1')
30         res_data['title'] = title_node.get_text()
31         
32         summary_node = soup.find('div', class_="lemma-summary")
33         res_data['summary'] = summary_node.get_text()
34         print res_data['summary']
35 
36         return res_data
37 
38     def parse(self, page_url, html_cont):
39         if page_url is None or html_cont is None:
40             return 
41 
42         soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
43         new_urls = self._get_new_urls(page_url, soup)
44         new_data = self._get_new_data(page_url, soup)
45         print new_data
46         return new_urls, new_data
47

html_outputer.py

 1 #!/usr/bin/python 
 2 #-*- coding:utf8 -*-
 3 
 4 class HtmlOutputer(object):
 5     def __init__(self):
 6         self.datas = []
 7 
 8     def collect_data(self, data):
 9         if data is None:
10             return
11         self.datas.append(data)
12         
13 
14     def output_html(self):
15         fout = open('output.html', 'w')
16 
17         fout.write("<html>")
18         fout.write("<body>")
19         fout.write("<head>")
20         fout.write('<meta charset="utf-8">')
21         fout.write("</head>")
22         fout.write("<table>")
23 
24         for data in self.datas:
25             fout.write("<tr>")
26             fout.write("<td>%s</td>" % data['url'])
27             fout.write("<td>%s</td>" % data['title'].encode('utf-8'))
28             fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
29             fout.write("</tr>")
30 
31         fout.write("</table>")
32         fout.write("</body>")
33         fout.write("</html>")
34 
35         fout.close()

html_downloader.py

 1 #!/usr/bin/python
 2 #-*- coding:utf8 -*-
 3 
 4 import urllib2
 5 
 6 class HtmlDownloader(object):
 7     '''
 8     下载器
 9     '''
10 
11     def download(self, url):
12         if url is None:
13             return None
14 
15         response = urllib2.urlopen(url)
16 
17         if response.getcode() != 200:
18             print '请求失败'
19             return None
20 
21         return response.read()

url_manager.py

 1 #!/usr/bin/python
 2 #-*- coding:utf8 -*-
 3 
 4 class UrlManager(object):
 5     '''
 6     url管理器
 7     '''
 8     def __init__(self):
 9         self.new_urls = set()
10         self.old_urls = set()
11 
12     def add_new_url(self, url):
13         if url is None:
14             return
15         if url not in self.new_urls and url not in self.old_urls:
16             self.new_urls.add(url)
17 
18     def has_new_url(self):
19         if len(self.new_urls) != 0:
20             return len(self.new_urls)
21         else:
22             print '没有新的url'
23 
24     def get_new_url(self):
25         new_url = self.new_urls.pop()
26         self.old_urls.add(new_url)
27         return new_url
28 
29     def add_new_urls(self, urls):
30         if urls is None or len(urls) == 0:
31             return 
32         for url in urls:
33             self.add_new_url(url)
34